LoMOE: Localized Multi-Object Editing via Multi-Diffusion
Introducing a novel framework for zero-shot localized multi-object editing through a multi-diffusion process to overcome challenges in precise image editing.
InstructBrush: Learning Attention-based Instruction Optimization for Image Editing
InstructBrush proposes a method for instruction-based image editing that optimizes editing instructions using attention-based techniques and transformation-oriented initialization, resulting in superior editing performance.
Diffusion Model-Based Image Editing: A Comprehensive Survey
Diffusion models are powerful tools for image editing, enabling high-quality sample generation by reversing the process of noise addition.
StableDrag: Stable Dragging for Point-based Image Editing
Designing a stable and precise drag-based editing framework, StableDrag, to enhance image manipulation through discriminative point tracking and confidence-based motion supervision.
StableDrag: Stable Dragging for Point-based Image Editing
The author presents the StableDrag framework to address inaccuracies in point tracking and incomplete motion supervision in image editing, aiming to achieve stable and precise drag performance.
Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
The author explores the role of cross and self-attention maps in image editing, highlighting the importance of self-attention for preserving image structure.
© 2024 by Linnk AI